@@ -79,7 +79,7 @@ class Type: v.addBool("enabled", True, "Enabled") v.addList("items", [], "Items", - mypickle.StrNoEscapeVar("", "", "")) + mypickle.StrLatin1Var("", "", "")) v.makeDicts() autocompletion.py @@ -99,10 +99,10 @@ class GlobalData: v.addInt("height", 830, "Height", 300, 9999) v.addInt("viewMode", VIEWMODE_LAYOUT, "ViewMode", VIEWMODE_DRAFT, VIEWMODE_OVERVIEW_LARGE) - v.addStr("license", "", "License") + v.addStrBinary("license", "", "License") v.addList("files", [], "Files", - mypickle.StrNoEscapeVar("", "", "")) + mypickle.StrUnicodeVar("", "", "")) v.makeDicts() v.setDefaults(self) @@ -165,8 +165,7 @@ class GlobalData: # save global spell checker dictionary to disk def saveScDict(self): - util.writeToFile(self.scDictFilename, - util.toUTF8(self.scDict.save()), mainFrame) + util.writeToFile(self.scDictFilename, self.scDict.save(), mainFrame) class MyPanel(wxPanel): @@ -2381,7 +2380,7 @@ class MyApp(wxApp): gd.setViewMode(gd.viewMode) if util.fileExists(gd.scDictFilename): - s = util.fromUTF8(util.loadFile(gd.scDictFilename, None)) + s = util.loadFile(gd.scDictFilename, None) if s: gd.scDict.load(s) blyte.py @@ -399,13 +399,13 @@ class Config: v.addInt("cursorColumn", 0, "Cursor/Column", 0, 1000000) # various strings we add to the script - v.addStrNoEscape("strMore", "(MORE)", "String/MoreDialogue") - v.addStrNoEscape("strContinuedPageEnd", "(CONTINUED)", - "String/ContinuedPageEnd") - v.addStrNoEscape("strContinuedPageStart", "CONTINUED:", - "String/ContinuedPageStart") - v.addStrNoEscape("strDialogueContinued", " (cont'd)", - "String/DialogueContinued") + v.addStrLatin1("strMore", "(MORE)", "String/MoreDialogue") + v.addStrLatin1("strContinuedPageEnd", "(CONTINUED)", + "String/ContinuedPageEnd") + v.addStrLatin1("strContinuedPageStart", "CONTINUED:", + "String/ContinuedPageStart") + v.addStrLatin1("strDialogueContinued", " (cont'd)", + "String/DialogueContinued") v.makeDicts() @@ -447,7 +447,7 @@ class Config: for it in el.cvars.numeric.itervalues(): util.clampObj(el, it.name, it.minVal, it.maxVal) - for it in self.cvars.stringNoEscape.itervalues(): + for it in self.cvars.stringLatin1.itervalues(): setattr(self, it.name, util.toInputStr(getattr(self, it.name))) # make sure usable space on the page isn't too small @@ -850,26 +850,27 @@ class ConfigGlobal: % wxPlatform s2 = "" - v.addStr("pdfViewerPath", s1, "PDF/ViewerPath") - v.addStr("pdfViewerArgs", s2, "PDF/ViewerArguments") + v.addStrUnicode("pdfViewerPath", s1, "PDF/ViewerPath") + v.addStrBinary("pdfViewerArgs", s2, "PDF/ViewerArguments") # fonts if misc.isUnix: - v.addStr("fontNormal", "0;-adobe-courier-medium-r-normal-*-*-140-*-*-m-*-iso8859-1", "FontNormal") - v.addStr("fontBold", "0;-adobe-courier-bold-r-normal-*-*-140-*-*-m-*-iso8859-1", "FontBold") - v.addStr("fontItalic", "0;-adobe-courier-medium-o-normal-*-*-140-*-*-m-*-iso8859-1", "FontItalic") - v.addStr("fontBoldItalic", "0;-adobe-courier-bold-o-normal-*-*-140-*-*-m-*-iso8859-1", "FontBoldItalic") + v.addStrBinary("fontNormal", "0;-adobe-courier-medium-r-normal-*-*-140-*-*-m-*-iso8859-1", "FontNormal") + v.addStrBinary("fontBold", "0;-adobe-courier-bold-r-normal-*-*-140-*-*-m-*-iso8859-1", "FontBold") + v.addStrBinary("fontItalic", "0;-adobe-courier-medium-o-normal-*-*-140-*-*-m-*-iso8859-1", "FontItalic") + v.addStrBinary("fontBoldItalic", "0;-adobe-courier-bold-o-normal-*-*-140-*-*-m-*-iso8859-1", "FontBoldItalic") elif misc.isWindows: - v.addStr("fontNormal", "0;-13;0;0;0;400;0;0;0;0;3;2;1;49;Courier New", "FontNormal") - v.addStr("fontBold", "0;-13;0;0;0;700;0;0;0;0;3;2;1;49;Courier New", "FontBold") - v.addStr("fontItalic", "0;-13;0;0;0;400;255;0;0;0;3;2;1;49;Courier New", "FontItalic") - v.addStr("fontBoldItalic", "0;-13;0;0;0;700;255;0;0;0;3;2;1;49;Courier New", "FontBoldItalic") + v.addStrBinary("fontNormal", "0;-13;0;0;0;400;0;0;0;0;3;2;1;49;Courier New", "FontNormal") + v.addStrBinary("fontBold", "0;-13;0;0;0;700;0;0;0;0;3;2;1;49;Courier New", "FontBold") + v.addStrBinary("fontItalic", "0;-13;0;0;0;400;255;0;0;0;3;2;1;49;Courier New", "FontItalic") + v.addStrBinary("fontBoldItalic", "0;-13;0;0;0;700;255;0;0;0;3;2;1;49;Courier New", "FontBoldItalic") else: raise ConfigError("unknown platform") # default script directory - v.addStr("scriptDir", misc.progPath, "DefaultScriptDirectory") + v.addStrUnicode("scriptDir", misc.progPath, + "DefaultScriptDirectory") # colors v.addColor("text", 0, 0, 0, "TextFG", "Text foreground") config.py @@ -95,7 +95,7 @@ class HeaderString: # # sample of the format: '1,0,r,,${PAGE}.' def load(self, s): - a = s.split(",", 4) + a = util.fromUTF8(s).split(",", 4) if len(a) != 5: return @@ -130,4 +130,4 @@ class HeaderString: s += ",,%s" % self.text - return s + return util.toUTF8(s) headers.py @@ -15,7 +15,7 @@ class Locations: v.addList("locations", [], "Locations", mypickle.ListVar("", [], "", - mypickle.StrNoEscapeVar("", "", ""))) + mypickle.StrLatin1Var("", "", ""))) v.makeDicts() locations.py @@ -17,7 +17,7 @@ class Vars: self.all = self.getDict() self.color = self.getDict(ColorVar) self.numeric = self.getDict(NumericVar) - self.stringNoEscape = self.getDict(StrNoEscapeVar) + self.stringLatin1 = self.getDict(StrLatin1Var) # return dictionary containing given type of variable objects, or all # if typeObj is None. @@ -100,11 +100,14 @@ class Vars: def addInt(self, *params): self.addVar(IntVar(*params)) - def addStr(self, *params): - self.addVar(StrVar(*params)) + def addStrLatin1(self, *params): + self.addVar(StrLatin1Var(*params)) - def addStrNoEscape(self, *params): - self.addVar(StrNoEscapeVar(*params)) + def addStrUnicode(self, *params): + self.addVar(StrUnicodeVar(*params)) + + def addStrBinary(self, *params): + self.addVar(StrBinaryVar(*params)) def addElemName(self, *params): self.addVar(ElementNameVar(*params)) @@ -176,30 +179,41 @@ class IntVar(NumericVar): def fromStr(self, vals, val, prefix): return util.str2int(val, self.defVal, self.minVal, self.maxVal) + +# ISO-8859-1 (Latin 1) string. +class StrLatin1Var(ConfVar): + def __init__(self, name, defVal, name2): + ConfVar.__init__(self, name, defVal, name2) -class StrVar(ConfVar): + def toStr(self, val, prefix): + return "%s:%s\n" % (prefix, util.toUTF8(val)) + + def fromStr(self, vals, val, prefix): + return util.fromUTF8(val) + +# Unicode string. +class StrUnicodeVar(ConfVar): def __init__(self, name, defVal, name2): ConfVar.__init__(self, name, defVal, name2) def toStr(self, val, prefix): - return "%s:%s\n" % (prefix, util.encodeStr(val)) + return "%s:%s\n" % (prefix, val.encode("UTF-8")) def fromStr(self, vals, val, prefix): - return util.decodeStr(val) + return val.decode("UTF-8", "ignore") -# like StrVar, but doesn't do any escaping. this is useful if you have -# e.g. Latin1 text without newlines that you want to transcode to UTF-8 -# later on, which is impossible to do with StrVar since it's escaped the -# Latin1 characters already. -class StrNoEscapeVar(ConfVar): +# binary string, can contain anything. characters outside of printable +# ASCII (and \ itself) are encoded as \XX, where XX is the hex code of the +# character. +class StrBinaryVar(ConfVar): def __init__(self, name, defVal, name2): ConfVar.__init__(self, name, defVal, name2) def toStr(self, val, prefix): - return "%s:%s\n" % (prefix, val) + return "%s:%s\n" % (prefix, util.encodeStr(val)) def fromStr(self, vals, val, prefix): - return val + return util.decodeStr(val) # screenplay.ACTION <-> "Action" class ElementNameVar(ConfVar): mypickle.py @@ -140,19 +140,19 @@ class Screenplay: output += "#Version 3\n" output += "#Begin-Auto-Completion \n" - output += util.toUTF8(self.autoCompletion.save()) + output += self.autoCompletion.save() output += "#End-Auto-Completion \n" output += "#Begin-Config \n" - output += util.toUTF8(self.cfg.save()) + output += self.cfg.save() output += "#End-Config \n" output += "#Begin-Locations \n" - output += util.toUTF8(self.locations.save()) + output += self.locations.save() output += "#End-Locations \n" output += "#Begin-Spell-Checker-Dict \n" - output += util.toUTF8(self.scDict.save()) + output += self.scDict.save() output += "#End-Spell-Checker-Dict \n" pgs = self.titles.pages @@ -161,10 +161,10 @@ class Screenplay: output += "#Title-Page \n" for i in xrange(len(pgs[pg])): - output += "#Title-String %s\n" % util.toUTF8(str(pgs[pg][i])) + output += "#Title-String %s\n" % str(pgs[pg][i]) for h in self.headers.hdrs: - output += "#Header-String %s\n" % util.toUTF8(str(h)) + output += "#Header-String %s\n" % str(h) output += "#Header-Empty-Lines %d\n" % self.headers.emptyLinesAfter @@ -190,32 +190,6 @@ class Screenplay: # remove default empty line sp.lines = [] - # did we encounter characters not in ISO-8859-1 - invalidChars = False - - # did we encounter characters in ISO-8859-1, but undesired - unwantedChars = False - - # convert to ISO-8859-1, remove invalid characters - for i in xrange(len(lines)): - try: - s = unicode(lines[i], "UTF-8") - except ValueError: - raise error.MiscError("Line %d contains invalid UTF-8 data." - % (i + 1)) - - try: - s = s.encode("ISO-8859-1") - except ValueError: - invalidChars = True - s = s.encode("ISO-8859-1", "backslashreplace") - - newS = util.toInputStr(s) - if s != newS: - unwantedChars = True - - lines[i] = newS - if len(lines) < 2: raise error.MiscError("File has too few lines to be a valid\n" "screenplay file.") @@ -314,7 +288,7 @@ class Screenplay: lb = config.char2lb(s[0], False) lt = config.char2lt(s[1], False) - text = s[2:] + text = util.toInputStr(util.fromUTF8(s[2:])) # convert unknown lb types into LB_SPACE if lb == None: @@ -375,18 +349,6 @@ class Screenplay: " You'll lose that information if you save over" " the existing file.") - if invalidChars: - msgs.append("Screenplay contained characters not in the" - " ISO-8859-1 character set, which is all that this" - " version of the program supports.\n\n" - " These characters have been converted to their" - " Unicode escape sequences. Search for '\u' to find" - " them.") - - if unwantedChars: - msgs.append("Screenplay contained invalid characters. These" - " characters have been converted to '|'.") - return (sp, "\n\n".join(msgs)) load = staticmethod(load) screenplay.py @@ -81,7 +81,7 @@ class Dict: v = self.__class__.cvars = mypickle.Vars() v.addList("wordsList", [], "Words", - mypickle.StrNoEscapeVar("", "", "")) + mypickle.StrLatin1Var("", "", "")) v.makeDicts() spellcheck.py @@ -134,7 +134,7 @@ class TitleString: # # sample of the format: '0.000000,70.000000,24,cb,Helvetica,,text here' def load(self, s): - a = s.split(",", 6) + a = util.fromUTF8(s).split(",", 6) if len(a) != 7: return @@ -170,4 +170,4 @@ class TitleString: s += ",,%s" % self.text - return s + return util.toUTF8(s) titles.py @@ -948,5 +948,8 @@ def showPDF(filename, cfgGl, frame): # give the full path of the program as first arg, so give a # dummy arg. args = ["pdf"] + cfgGl.pdfViewerArgs.split() + [filename] - + + # FIXME: investigate if spawnv supports unicode string as program name + # in Python 2.3 (maybe also test Python 2.4 and switch to it on + # Windows if needed?) os.spawnv(os.P_NOWAIT, cfgGl.pdfViewerPath, args) util.py 105aaea03107a43254d26025ee4c1ceac04555e4 Osku Salerma osku@iki.fi http://github.com/oskusalerma/blyte/commit/4f76a9379bf2715ca513b4688ef8041ce65ae4f8 4f76a9379bf2715ca513b4688ef8041ce65ae4f8 2006-03-04T22:58:10-08:00 2006-03-04T22:58:10-08:00 Add Str(Latin1|Unicode|Binary)Var to mypickle and change everyone to use them. Remove global toUTF8/fromUTF8 calls since everyone is now responsible for their own encodings. 70831e301f5ac2f0d7f246317dff61934192a607 Osku Salerma osku@iki.fi